Learning the Distribution Map in Reverse Causal Performative Prediction
Daniele Bracale, Subha Maity, Yuekai Sun, Moulinath Banerjee
Abstract
In numerous predictive scenarios, the predictive model affects the sampling distribution; for example, job applicants often meticulously craft their resumes to navigate through a screening system. Such shifts in distribution are particularly prevalent in social computing, yet, the strategies to learn these shifts from data remain remarkably limited. Inspired by a microeconomic model that adeptly characterizes agents' behavior within labor markets, we introduce a novel approach to learning the distribution shift. Our method is predicated on a \emph{reverse causal model}, wherein the predictive model instigates a distribution shift exclusively through a finite set of agents' actions. Within this framework, we employ a microfoundation model for the agents' actions and develop a statistically justified methodology to learn the distribution shift map, which we demonstrate to effectively minimize the performative prediction risk.
BibTeX
@inproceedings{
bracale2025learning,
title={Learning the Distribution Map in Reverse Causal Performative Prediction},
author={Daniele Bracale and Subha Maity and Yuekai Sun and Moulinath Banerjee},
booktitle={The 28th International Conference on Artificial Intelligence and Statistics},
year={2025},
url={https://openreview.net/forum?id=rVEVn0MaVF}
}